Visual stimuli elicit waves of activity that propagate across the visual cortex of turtles. It is believed that these activity waves encode features of the visual stimuli, viz. position and velocity of targets. An important problem is to estimate the target location from the activity waves of the visual cortex. In this paper, we have used a large scale model of the turtle visual cortex to simulate the response of the cortex to stationary and moving visual stimuli. Subsequently, we have estimated the position and velocity of the target from the neural activities of the cortex by constructing an Autoregressive and Moving Average (ARMA) Model. The input to the model is the neuronal response suitably smoothed by a low pass filter. The output of the ARMA model is precisely the prediction of the cortical inputs. This paper illustrates the role of ARMA models in deciphering the location and velocity of visual targets from the associated cortical waves.